About

Man smiling with hand in pocket

Prior to pursuing PhD under supervision of Brian Scassellati, I completed my B.S. in artificial intelligence (AI) with a concentration in human-computer interaction (HCI) at Carnegie Mellon University in 2022, where I was part of the Transportation, Bots, and Disability (TBD) Lab supervised by Aaron Steinfeld. Additionally, I was a member of the School of Computer Science Dean's Undergraduate Advisory Committee, as well as a founder and chair of the Accommodations for Blind and Deaf Students Subcommittee.

I am passionate about promoting better accessibility to daily activities for individuals with disabilities. As a member of the Southington Dementia Positive Movement, I collaborate with professionals and community leaders to brainstorm ideas and take meaningful steps toward recognizing how everyone—regardless of age or ability—can contribute to society. Previously, I served on the Disability Pride PA Committee, organizing events across Pennsylvania to celebrate and advocate for disability inclusion and awareness.

I'm open to internships and co-ops starting in summer 2025!

fern.limprayoon@yale.edu
Get in touch!

Experience

Download CV

Education

  • PhD in Computer Science Yale University Expected May 2028
  • BS in Artificial Intelligence Carnegie Mellon University May 2022

Academia

Graduate Research Assistant

december 2024 now social robotics lab, yale university

Collaborating with the Yale School of Public Health and the LiveWell Institute to co-design behaviors for a social robot, aimed at facilitating activities that strengthen relationships between individuals living with dementia and their care partners.

Undergraduate Research Assistant

september 2019 may 2022 TBD Lab, Carnegie Mellon University

Designed and developed a path planning algorithm to make the robot's movements safer and more socially appropriate.

Collaborated with an orientation and mobility specialist to get feedback and incorporated their suggestions to improve the system's design.

Created a system that uses environmental sensor data to direct users to fixed targets with audio cues and vibrotactile feedback.

Summer Undergraduate Research Fellowship

june 2021 august 2021 stanford hci group

Led a study on how GPT-3 can predict potential conversation breakdowns before any observable psycholinguistic changes, aiding in more effective content moderation.

Industry

Software Development Intern

may 2019 august 2019 scb abacus (now: abacus digital)

Created a software development kit (SDK) for a mobile lending platform that serves the underbanked population in Thailand, called MoneyThunder. The SDK functions as a pipeline that asynchronously processes user data from IOS and Android mobile devices, transforms raw data, sends them to cloud storage, and notifies backend services.

Product Management Intern

june 2017 july 2017 Kasikorn Business Technology Group

Completed the design of customer journey, UI prototype mockups and defined the business metrics for four features on lifestyle banking and merchant mobile apps.

Projects

News

  • 29 AUG 2022 Presented our paper on The Effects of a Gossiping Robot on Team Cohesion at ROMAN
  • 15 AUG 2022 Starting my PhD in Computer Science at Yale
  • 15 MAY 2022 Graduated with a BS in Artificial Intelligence from Carnegie Mellon University
  • 12 MAY 2022 Nominated as a Senior Leadership Recognition Recipient
  • 04 MAY 2022 Presented my senior thesis at Meeting of the Minds Undergraduate Research Symposium
  • 31 MAR 2022 Co-led CS TA Seminar with Lauren Johnson on How to Better Support Students with Accommodations
  • 06 NOV 2021 Selected as 1 of 15 seniors for early induction into Phi Beta Kappa
  • 20 OCT 2021 Presented our poster on Robot Trajectories When Approaching a User with a Visual Impairment at ASSETS
  • 12 AUG 2021 As 1 of 25 scholars selected for Stanford SURF, I presented my research with the Stanford HCI Group at the poster session.

The Effects of a Gossiping Robot on Team Cohesion

Jirachaya "Fern" Limprayoon, Nicholas C. Georgiou, Natnaree "Proud" Ua-Arak, Brian Scassellati

Categories conference ROMAN'2024
Download Paper
Preview Image of The Effects of a Gossiping Robot on Team Cohesion

Abstract

Gossip is a human behavior that has been shown to strengthen bonds, trust, and the feeling of inclusion between the gossiper and the person with whom they share the gossip. As humans engage more with social robots, fostering bonds between them is critical for meaningful interactions. In this paper, we investigated how gossiping can affect the perception of group inclusion and trust between a human and a robot. In this between-subjects user study (N = 38), we compared the effects of a robot that gossips to the participant in either a positive or negative way about the experimenter during an interaction. We found that participants in the positive condition reported a significant increase in group inclusion with the robot, while participants in the negative condition did not. We also found that participants’ moral trust in the negative condition significantly decreased. Our results suggested that positive gossip can be beneficial to human-robot team cohesion.

Recommended Citation

Jirachaya "Fern" Limprayoon, Nicholas C. Georgiou, Natnaree "Proud" Ua-Arak, and Brian Scassellati. 2024. The Effects of a Gossiping Robot on Team Cohesion. In The 33rd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), August 26-30, 2024, Pasedena CA, USA. IEEE, Pasedena, CA, USA 6 Pages.

Path Guiding for People with Visual Impairments for Short-Range Rendezvous with a Static Target

Categories thesis
Download Paper
Poster Image of Path Guiding for People with Visual Impairments for Short-Range Rendezvous with a Static Target

CS Senior Honors Thesis

Abstract

Navigating in complex indoor spaces like train stations, shopping malls, and university buildings can be challenging for people with visual impairments, since current path planning approaches rely on users to spontaneously adjust their trajectories based on their visual knowledge. To help a user with a visual impairment rendezvous with a static object (e.g., a waiting robot, a kiosk, or an autonomous car at the curbside) in a seamless way, we propose an approach that can incorporate information about the user’s position and orientation from sensors attached to the environment, nearby robots, or cars to dynamically plan and give users instructions of how to reach their goal.

Robot Trajectories When Approaching a User with a Visual Impairment

Jirachaya "Fern" Limprayoon, Prithu Pareek, Xiang Zhi Tan, Aaron Steinfeld

Categories poster ASSETS'2021
Download Paper
A preview image of Robot Trajectories When Approaching a User with a Visual Impairment

Abstract

Mobile robots have been shown to be helpful in guiding users in complex indoor spaces. While these robots can assist all types of users, current implementations often rely on users visually rendezvousing with the robot, which may be a challenge for people with visual impairments. This paper describes a proof of concept for a robotic system that addresses this kind of short-range rendezvous for users with visual impairments. We propose to use a lattice graph-based Anytime Repairing A* (ARA*) planner as a global planner to discourage the robot from turning in place at its goal position, making its path more human-like and safer. We also interviewed an Orientation & Mobility (O&M) Specialist for their thoughts on our planner. They observed that our planner produces less obtrusive trajectories to the user than the ROS default global planner and recommended that our system should allow the robot to approach the person from the side as opposed to the front as it currently does. In the future, we plan to test our system with users in-person to better validate our assumptions and find additional pain points.

Recommended Citation

Recommended citation: Jirachaya "Fern" Limprayoon, Prithu Pareek, Xiang Zhi Tan, and Aaron Steinfeld. 2021. Robot Trajectories When Approaching a User with a Visual Impairment. In The 23rd International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS '21), October 18-22, 2021, Virtual Event, USA. ACM, New York, NY, USA 4 Pages.

Understanding How Self-Fulfilling Prophecy Plays a Role in Conversation with Language Model

Jirachaya "Fern" Limprayoon, Joon Sung Park, Mitchell L. Gordon, Ranjay Krishna, Michael S. Bernstein

Categories poster
Preview Image of Understanding How Self-Fulfilling Prophecy Plays a Role in Conversation with Language Model

Stanford SURF Poster

Abstract

With the rise of artificial intelligence, chatbots have become more generative, meaning that they are capable of learning from input queries and responding to them on the fly. Generative chatbots are trained on human-human conversations, where self-fulfilling prophecy is proven to play a role. An example of self-fulfilling prophecy might be when you believe that the other party is nice and accepting then go out of your way to start a conversation and act friendly around them. The other party then see you seem to like them and act friendly in response, leading you to think that the other party lives up to their nice reputation. However, the resulting desirable interaction is mostly a result of your initial belief. Our research focuses on understanding if a language model like GPT-3 can mimic the way humans talk to it and potentially in line with the beliefs humans have about it, which can help us understand if self-fulfilling prophecy phenomenon can happen during such interaction. Understanding it can really help us take control and moderate the human-chatbot interactions to ensure that they abide by specific community guidelines.

Thai Help Thai

Chakara Orawang, Supawat Vitoorapakorn, Jirachaya "Fern" Limprayoon, Natjanan Mongkolsupawan,
Peerat Vichivanives, Piratach Yoovidhya, Natnaree Tangwiwat

Categories design website
Project Website
Preview Image of Thai Help Thai

Summary

Many Thai students in the US, whether funded by the Thai government or private sponsors, aim to use their knowledge to support Thailand's social and economic progress. However, a lack of centralized platforms limits their ability to connect with peers, professionals, and stakeholders. To address this, our team proposed a networking platform to foster collaboration and build connections among Thai students and related stakeholders.

Client

Royal Thai Embassy

A big fake project

Categories photo branding
Fake project image for demonstration purposes only
Fake project image for demonstration purposes only
Fake project image for demonstration purposes only

Description

This is a fake text, it is used to fill some text area that doesn't have any content written yet. It simulates how the paragraph will look like. Remember to edit this content before publishing your project.

Client

ACME Company

Skills

  • PHP
  • HTML
  • CSS
esc